Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 19824
    Prev
    Next
    INDEX
    Explanations

    words related to convincing or persuading someone

    oai_token-act-pair · gpt-3.5-turbo

    words related to a person named "Vin" or phrases containing "Vin"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.79
    awei
    -0.74
    arers
    -0.70
    ropolitan
    -0.65
    akening
    -0.63
    ngth
    -0.61
    berman
    -0.60
    retched
    -0.59
    erity
    -0.59
     graduates
    -0.59
    POSITIVE LOGITS
    idia
    1.02
    osaurs
    0.94
    jury
    0.94
    eland
    0.94
    iti
    0.93
    ces
    0.91
    warm
    0.87
    eteen
    0.86
    itive
    0.84
    cent
    0.83
    Activations Density 0.054%

    No Known Activations